Author:
Hou Yongjie,Yang Qingwen,Li Li,Shi Gang
Abstract
In view of the fact that the aerial images of UAVs are usually taken from a top-down perspective, there are large changes in spatial resolution and small targets to be detected, and the detection method of natural scenes is not effective in detecting under the arbitrary arrangement of remote sensing image direction, which is difficult to apply to the detection demand scenario of road technology status assessment, this paper proposes a lightweight network architecture algorithm based on MobileNetv3-YOLOv5s (MR-YOLO). First, the MobileNetv3 structure is introduced to replace part of the backbone network of YOLOv5s for feature extraction so as to reduce the network model size and computation and improve the detection speed of the target; meanwhile, the CSPNet cross-stage local network is introduced to ensure the accuracy while reducing the computation. The focal loss function is improved to improve the localization accuracy while increasing the speed of the bounding box regression. Finally, by improving the YOLOv5 target detection network from the prior frame design and the bounding box regression formula, the rotation angle method is added to make it suitable for the detection demand scenario of road technology status assessment. After a large number of algorithm comparisons and data ablation experiments, the feasibility of the algorithm was verified on the Xinjiang Altay highway dataset, and the accuracy of the MR-YOLO algorithm was as high as 91.1%, the average accuracy was as high as 92.4%, and the detection speed reached 96.8 FPS. Compared with YOLOv5s, the p-value and mAP values of the proposed algorithm were effectively improved. It can be seen that the proposed algorithm improves the detection accuracy and detection speed while greatly reducing the number of model parameters and computation.
Funder
National Natural Science Foundation of China
the Third Xinjiang Scientific Expedition Program
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference41 articles.
1. A new methodology for non-contact accurate crack width measurement through photogrammetry for automated structural safety evaluation;Mohammad;Smart Mater. Struct.,2013
2. Automated inspection and restoration of steel bridges—A critical review of methods and enabling technologies;McCrea;Autom. Constr.,2002
3. Computer vision techniques for construction safety and health monitoring;JoonOh;Adv. Eng. Inform.,2015
4. Chen, J., Wu, J., Chen, G., Dong, W., and Sheng, X. (2016). International Conference on Intelligent Robotics and Applications, Springer.
5. ImageNet classification with deep convolutional neural networks;Alex;Commun. ACM,2017
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献